OpenCloudOS-Kernel/fs/xfs/xfs_super.c

1967 lines
50 KiB
C
Raw Normal View History

/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_bmap.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_fsops.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_da_btree.h"
#include "xfs_dir2.h"
#include "xfs_extfree_item.h"
#include "xfs_mru_cache.h"
#include "xfs_inode_item.h"
#include "xfs_icache.h"
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
#include "xfs_trace.h"
#include "xfs_icreate_item.h"
#include "xfs_filestream.h"
#include "xfs_quota.h"
#include "xfs_sysfs.h"
#include "xfs_ondisk.h"
#include <linux/namei.h>
#include <linux/init.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/mempool.h>
#include <linux/writeback.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/parser.h>
static const struct super_operations xfs_super_operations;
struct bio_set *xfs_ioend_bioset;
static struct kset *xfs_kset; /* top-level xfs sysfs dir */
#ifdef DEBUG
static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */
#endif
/*
* Table driven mount option parser.
*/
enum {
Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_biosize,
Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid,
Opt_mtpt, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups,
Opt_allocsize, Opt_norecovery, Opt_barrier, Opt_nobarrier,
Opt_inode64, Opt_inode32, Opt_ikeep, Opt_noikeep,
Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2, Opt_filestreams,
Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota,
Opt_uquota, Opt_gquota, Opt_pquota,
Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
Opt_discard, Opt_nodiscard, Opt_dax, Opt_err,
};
static const match_table_t tokens = {
{Opt_logbufs, "logbufs=%u"}, /* number of XFS log buffers */
{Opt_logbsize, "logbsize=%s"}, /* size of XFS log buffers */
{Opt_logdev, "logdev=%s"}, /* log device */
{Opt_rtdev, "rtdev=%s"}, /* realtime I/O device */
{Opt_biosize, "biosize=%u"}, /* log2 of preferred buffered io size */
{Opt_wsync, "wsync"}, /* safe-mode nfs compatible mount */
{Opt_noalign, "noalign"}, /* turn off stripe alignment */
{Opt_swalloc, "swalloc"}, /* turn on stripe width allocation */
{Opt_sunit, "sunit=%u"}, /* data volume stripe unit */
{Opt_swidth, "swidth=%u"}, /* data volume stripe width */
{Opt_nouuid, "nouuid"}, /* ignore filesystem UUID */
{Opt_mtpt, "mtpt"}, /* filesystem mount point */
{Opt_grpid, "grpid"}, /* group-ID from parent directory */
{Opt_nogrpid, "nogrpid"}, /* group-ID from current process */
{Opt_bsdgroups, "bsdgroups"}, /* group-ID from parent directory */
{Opt_sysvgroups,"sysvgroups"}, /* group-ID from current process */
{Opt_allocsize, "allocsize=%s"},/* preferred allocation size */
{Opt_norecovery,"norecovery"}, /* don't run XFS recovery */
{Opt_barrier, "barrier"}, /* use writer barriers for log write and
* unwritten extent conversion */
{Opt_nobarrier, "nobarrier"}, /* .. disable */
{Opt_inode64, "inode64"}, /* inodes can be allocated anywhere */
{Opt_inode32, "inode32"}, /* inode allocation limited to
* XFS_MAXINUMBER_32 */
{Opt_ikeep, "ikeep"}, /* do not free empty inode clusters */
{Opt_noikeep, "noikeep"}, /* free empty inode clusters */
{Opt_largeio, "largeio"}, /* report large I/O sizes in stat() */
{Opt_nolargeio, "nolargeio"}, /* do not report large I/O sizes
* in stat(). */
{Opt_attr2, "attr2"}, /* do use attr2 attribute format */
{Opt_noattr2, "noattr2"}, /* do not use attr2 attribute format */
{Opt_filestreams,"filestreams"},/* use filestreams allocator */
{Opt_quota, "quota"}, /* disk quotas (user) */
{Opt_noquota, "noquota"}, /* no quotas */
{Opt_usrquota, "usrquota"}, /* user quota enabled */
{Opt_grpquota, "grpquota"}, /* group quota enabled */
{Opt_prjquota, "prjquota"}, /* project quota enabled */
{Opt_uquota, "uquota"}, /* user quota (IRIX variant) */
{Opt_gquota, "gquota"}, /* group quota (IRIX variant) */
{Opt_pquota, "pquota"}, /* project quota (IRIX variant) */
{Opt_uqnoenforce,"uqnoenforce"},/* user quota limit enforcement */
{Opt_gqnoenforce,"gqnoenforce"},/* group quota limit enforcement */
{Opt_pqnoenforce,"pqnoenforce"},/* project quota limit enforcement */
{Opt_qnoenforce, "qnoenforce"}, /* same as uqnoenforce */
{Opt_discard, "discard"}, /* Discard unused blocks */
{Opt_nodiscard, "nodiscard"}, /* Do not discard unused blocks */
{Opt_dax, "dax"}, /* Enable direct access to bdev pages */
{Opt_err, NULL},
};
STATIC int
suffix_kstrtoint(const substring_t *s, unsigned int base, int *res)
{
int last, shift_left_factor = 0, _res;
char *value;
int ret = 0;
value = match_strdup(s);
if (!value)
return -ENOMEM;
last = strlen(value) - 1;
if (value[last] == 'K' || value[last] == 'k') {
shift_left_factor = 10;
value[last] = '\0';
}
if (value[last] == 'M' || value[last] == 'm') {
shift_left_factor = 20;
value[last] = '\0';
}
if (value[last] == 'G' || value[last] == 'g') {
shift_left_factor = 30;
value[last] = '\0';
}
if (kstrtoint(value, base, &_res))
ret = -EINVAL;
kfree(value);
*res = _res << shift_left_factor;
return ret;
}
/*
* This function fills in xfs_mount_t fields based on mount args.
* Note: the superblock has _not_ yet been read in.
*
* Note that this function leaks the various device name allocations on
* failure. The caller takes care of them.
*
* *sb is const because this is also used to test options on the remount
* path, and we don't want this to have any side effects at remount time.
* Today this function does not change *sb, but just to future-proof...
*/
STATIC int
xfs_parseargs(
struct xfs_mount *mp,
char *options)
{
const struct super_block *sb = mp->m_super;
char *p;
substring_t args[MAX_OPT_ARGS];
int dsunit = 0;
int dswidth = 0;
int iosize = 0;
__uint8_t iosizelog = 0;
/*
* set up the mount name first so all the errors will refer to the
* correct device.
*/
mp->m_fsname = kstrndup(sb->s_id, MAXNAMELEN, GFP_KERNEL);
if (!mp->m_fsname)
return -ENOMEM;
mp->m_fsname_len = strlen(mp->m_fsname) + 1;
/*
* Copy binary VFS mount flags we are interested in.
*/
if (sb->s_flags & MS_RDONLY)
mp->m_flags |= XFS_MOUNT_RDONLY;
if (sb->s_flags & MS_DIRSYNC)
mp->m_flags |= XFS_MOUNT_DIRSYNC;
if (sb->s_flags & MS_SYNCHRONOUS)
mp->m_flags |= XFS_MOUNT_WSYNC;
/*
* Set some default flags that could be cleared by the mount option
* parsing.
*/
mp->m_flags |= XFS_MOUNT_BARRIER;
mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
/*
* These can be overridden by the mount option parsing.
*/
mp->m_logbufs = -1;
mp->m_logbsize = -1;
if (!options)
goto done;
while ((p = strsep(&options, ",")) != NULL) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_logbufs:
if (match_int(args, &mp->m_logbufs))
return -EINVAL;
break;
case Opt_logbsize:
if (suffix_kstrtoint(args, 10, &mp->m_logbsize))
return -EINVAL;
break;
case Opt_logdev:
mp->m_logname = match_strdup(args);
if (!mp->m_logname)
return -ENOMEM;
break;
case Opt_mtpt:
xfs_warn(mp, "%s option not allowed on this system", p);
return -EINVAL;
case Opt_rtdev:
mp->m_rtname = match_strdup(args);
if (!mp->m_rtname)
return -ENOMEM;
break;
case Opt_allocsize:
case Opt_biosize:
if (suffix_kstrtoint(args, 10, &iosize))
return -EINVAL;
iosizelog = ffs(iosize) - 1;
break;
case Opt_grpid:
case Opt_bsdgroups:
mp->m_flags |= XFS_MOUNT_GRPID;
break;
case Opt_nogrpid:
case Opt_sysvgroups:
mp->m_flags &= ~XFS_MOUNT_GRPID;
break;
case Opt_wsync:
mp->m_flags |= XFS_MOUNT_WSYNC;
break;
case Opt_norecovery:
mp->m_flags |= XFS_MOUNT_NORECOVERY;
break;
case Opt_noalign:
mp->m_flags |= XFS_MOUNT_NOALIGN;
break;
case Opt_swalloc:
mp->m_flags |= XFS_MOUNT_SWALLOC;
break;
case Opt_sunit:
if (match_int(args, &dsunit))
return -EINVAL;
break;
case Opt_swidth:
if (match_int(args, &dswidth))
return -EINVAL;
break;
case Opt_inode32:
mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
break;
case Opt_inode64:
mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
break;
case Opt_nouuid:
mp->m_flags |= XFS_MOUNT_NOUUID;
break;
case Opt_barrier:
mp->m_flags |= XFS_MOUNT_BARRIER;
break;
case Opt_nobarrier:
mp->m_flags &= ~XFS_MOUNT_BARRIER;
break;
case Opt_ikeep:
mp->m_flags |= XFS_MOUNT_IKEEP;
break;
case Opt_noikeep:
mp->m_flags &= ~XFS_MOUNT_IKEEP;
break;
case Opt_largeio:
mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
break;
case Opt_nolargeio:
mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
break;
case Opt_attr2:
mp->m_flags |= XFS_MOUNT_ATTR2;
break;
case Opt_noattr2:
mp->m_flags &= ~XFS_MOUNT_ATTR2;
mp->m_flags |= XFS_MOUNT_NOATTR2;
break;
case Opt_filestreams:
mp->m_flags |= XFS_MOUNT_FILESTREAMS;
break;
case Opt_noquota:
mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
break;
case Opt_quota:
case Opt_uquota:
case Opt_usrquota:
mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
XFS_UQUOTA_ENFD);
break;
case Opt_qnoenforce:
case Opt_uqnoenforce:
mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_UQUOTA_ENFD;
break;
case Opt_pquota:
case Opt_prjquota:
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
XFS_PQUOTA_ENFD);
break;
case Opt_pqnoenforce:
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_PQUOTA_ENFD;
break;
case Opt_gquota:
case Opt_grpquota:
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
XFS_GQUOTA_ENFD);
break;
case Opt_gqnoenforce:
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_GQUOTA_ENFD;
break;
case Opt_discard:
mp->m_flags |= XFS_MOUNT_DISCARD;
break;
case Opt_nodiscard:
mp->m_flags &= ~XFS_MOUNT_DISCARD;
break;
#ifdef CONFIG_FS_DAX
case Opt_dax:
mp->m_flags |= XFS_MOUNT_DAX;
break;
#endif
default:
xfs_warn(mp, "unknown mount option [%s].", p);
return -EINVAL;
}
}
/*
* no recovery flag requires a read-only mount
*/
if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
!(mp->m_flags & XFS_MOUNT_RDONLY)) {
xfs_warn(mp, "no-recovery mounts must be read-only.");
return -EINVAL;
}
if ((mp->m_flags & XFS_MOUNT_NOALIGN) && (dsunit || dswidth)) {
xfs_warn(mp,
"sunit and swidth options incompatible with the noalign option");
return -EINVAL;
}
#ifndef CONFIG_XFS_QUOTA
if (XFS_IS_QUOTA_RUNNING(mp)) {
xfs_warn(mp, "quota support not available in this kernel.");
return -EINVAL;
}
#endif
if ((dsunit && !dswidth) || (!dsunit && dswidth)) {
xfs_warn(mp, "sunit and swidth must be specified together");
return -EINVAL;
}
if (dsunit && (dswidth % dsunit != 0)) {
xfs_warn(mp,
"stripe width (%d) must be a multiple of the stripe unit (%d)",
dswidth, dsunit);
return -EINVAL;
}
done:
if (dsunit && !(mp->m_flags & XFS_MOUNT_NOALIGN)) {
/*
* At this point the superblock has not been read
* in, therefore we do not know the block size.
* Before the mount call ends we will convert
* these to FSBs.
*/
mp->m_dalign = dsunit;
mp->m_swidth = dswidth;
}
if (mp->m_logbufs != -1 &&
mp->m_logbufs != 0 &&
(mp->m_logbufs < XLOG_MIN_ICLOGS ||
mp->m_logbufs > XLOG_MAX_ICLOGS)) {
xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]",
mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
return -EINVAL;
}
if (mp->m_logbsize != -1 &&
mp->m_logbsize != 0 &&
(mp->m_logbsize < XLOG_MIN_RECORD_BSIZE ||
mp->m_logbsize > XLOG_MAX_RECORD_BSIZE ||
!is_power_of_2(mp->m_logbsize))) {
xfs_warn(mp,
"invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
mp->m_logbsize);
return -EINVAL;
}
if (iosizelog) {
if (iosizelog > XFS_MAX_IO_LOG ||
iosizelog < XFS_MIN_IO_LOG) {
xfs_warn(mp, "invalid log iosize: %d [not %d-%d]",
iosizelog, XFS_MIN_IO_LOG,
XFS_MAX_IO_LOG);
return -EINVAL;
}
mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
mp->m_readio_log = iosizelog;
mp->m_writeio_log = iosizelog;
}
return 0;
}
struct proc_xfs_info {
uint64_t flag;
char *str;
};
STATIC int
xfs_showargs(
struct xfs_mount *mp,
struct seq_file *m)
{
static struct proc_xfs_info xfs_info_set[] = {
/* the few simple ones we can get from the mount struct */
{ XFS_MOUNT_IKEEP, ",ikeep" },
{ XFS_MOUNT_WSYNC, ",wsync" },
{ XFS_MOUNT_NOALIGN, ",noalign" },
{ XFS_MOUNT_SWALLOC, ",swalloc" },
{ XFS_MOUNT_NOUUID, ",nouuid" },
{ XFS_MOUNT_NORECOVERY, ",norecovery" },
{ XFS_MOUNT_ATTR2, ",attr2" },
{ XFS_MOUNT_FILESTREAMS, ",filestreams" },
{ XFS_MOUNT_GRPID, ",grpid" },
{ XFS_MOUNT_DISCARD, ",discard" },
{ XFS_MOUNT_SMALL_INUMS, ",inode32" },
{ XFS_MOUNT_DAX, ",dax" },
{ 0, NULL }
};
static struct proc_xfs_info xfs_info_unset[] = {
/* the few simple ones we can get from the mount struct */
{ XFS_MOUNT_COMPAT_IOSIZE, ",largeio" },
{ XFS_MOUNT_BARRIER, ",nobarrier" },
{ XFS_MOUNT_SMALL_INUMS, ",inode64" },
{ 0, NULL }
};
struct proc_xfs_info *xfs_infop;
for (xfs_infop = xfs_info_set; xfs_infop->flag; xfs_infop++) {
if (mp->m_flags & xfs_infop->flag)
seq_puts(m, xfs_infop->str);
}
for (xfs_infop = xfs_info_unset; xfs_infop->flag; xfs_infop++) {
if (!(mp->m_flags & xfs_infop->flag))
seq_puts(m, xfs_infop->str);
}
if (mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)
seq_printf(m, ",allocsize=%dk",
(int)(1 << mp->m_writeio_log) >> 10);
if (mp->m_logbufs > 0)
seq_printf(m, ",logbufs=%d", mp->m_logbufs);
if (mp->m_logbsize > 0)
seq_printf(m, ",logbsize=%dk", mp->m_logbsize >> 10);
if (mp->m_logname)
seq_show_option(m, "logdev", mp->m_logname);
if (mp->m_rtname)
seq_show_option(m, "rtdev", mp->m_rtname);
if (mp->m_dalign > 0)
seq_printf(m, ",sunit=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_dalign));
if (mp->m_swidth > 0)
seq_printf(m, ",swidth=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_swidth));
if (mp->m_qflags & (XFS_UQUOTA_ACCT|XFS_UQUOTA_ENFD))
seq_puts(m, ",usrquota");
else if (mp->m_qflags & XFS_UQUOTA_ACCT)
seq_puts(m, ",uqnoenforce");
xfs: xfs_showargs() reports group *and* project quotas enabled If you enable group or project quotas on an XFS file system, then the mount table presented through /proc/self/mounts erroneously shows that both options are in effect for the file system. The root of the problem is some bad logic in the xfs_showargs() function, which is used to format the file system type-specific options in effect for a file system. The problem originated in this GIT commit: Move platform specific mount option parse out of core XFS code Date: 11/22/07 Author: Dave Chinner SHA1 ID: a67d7c5f5d25d0b13a4dfb182697135b014fa478 For XFS quotas, project and group quota management are mutually exclusive--only one can be in effect at a time. There are two parts to managing quotas: aggregating usage information; and enforcing limits. It is possible to have a quota in effect (aggregating usage) but not enforced. These features are recorded on an XFS mount point using these flags: XFS_PQUOTA_ACCT - Project quotas are aggregated XFS_GQUOTA_ACCT - Group quotas are aggregated XFS_OQUOTA_ENFD - Project/group quotas are enforced The code in error is in fs/xfs/linux-2.6/xfs_super.c: if (mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_PRJQUOTA); else if (mp->m_qflags & XFS_PQUOTA_ACCT) seq_puts(m, "," MNTOPT_PQUOTANOENF); if (mp->m_qflags & (XFS_GQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_GRPQUOTA); else if (mp->m_qflags & XFS_GQUOTA_ACCT) seq_puts(m, "," MNTOPT_GQUOTANOENF); The problem is that XFS_OQUOTA_ENFD will be set in mp->m_qflags if either group or project quotas are enforced, and as a result both MNTOPT_PRJQUOTA and MNTOPT_GRPQUOTA will be shown as mount options. Signed-off-by: Alex Elder <aelder@sgi.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Felix Blyakher <felixb@sgi.com>
2009-09-03 06:02:24 +08:00
if (mp->m_qflags & XFS_PQUOTA_ACCT) {
if (mp->m_qflags & XFS_PQUOTA_ENFD)
seq_puts(m, ",prjquota");
xfs: xfs_showargs() reports group *and* project quotas enabled If you enable group or project quotas on an XFS file system, then the mount table presented through /proc/self/mounts erroneously shows that both options are in effect for the file system. The root of the problem is some bad logic in the xfs_showargs() function, which is used to format the file system type-specific options in effect for a file system. The problem originated in this GIT commit: Move platform specific mount option parse out of core XFS code Date: 11/22/07 Author: Dave Chinner SHA1 ID: a67d7c5f5d25d0b13a4dfb182697135b014fa478 For XFS quotas, project and group quota management are mutually exclusive--only one can be in effect at a time. There are two parts to managing quotas: aggregating usage information; and enforcing limits. It is possible to have a quota in effect (aggregating usage) but not enforced. These features are recorded on an XFS mount point using these flags: XFS_PQUOTA_ACCT - Project quotas are aggregated XFS_GQUOTA_ACCT - Group quotas are aggregated XFS_OQUOTA_ENFD - Project/group quotas are enforced The code in error is in fs/xfs/linux-2.6/xfs_super.c: if (mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_PRJQUOTA); else if (mp->m_qflags & XFS_PQUOTA_ACCT) seq_puts(m, "," MNTOPT_PQUOTANOENF); if (mp->m_qflags & (XFS_GQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_GRPQUOTA); else if (mp->m_qflags & XFS_GQUOTA_ACCT) seq_puts(m, "," MNTOPT_GQUOTANOENF); The problem is that XFS_OQUOTA_ENFD will be set in mp->m_qflags if either group or project quotas are enforced, and as a result both MNTOPT_PRJQUOTA and MNTOPT_GRPQUOTA will be shown as mount options. Signed-off-by: Alex Elder <aelder@sgi.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Felix Blyakher <felixb@sgi.com>
2009-09-03 06:02:24 +08:00
else
seq_puts(m, ",pqnoenforce");
}
if (mp->m_qflags & XFS_GQUOTA_ACCT) {
if (mp->m_qflags & XFS_GQUOTA_ENFD)
seq_puts(m, ",grpquota");
xfs: xfs_showargs() reports group *and* project quotas enabled If you enable group or project quotas on an XFS file system, then the mount table presented through /proc/self/mounts erroneously shows that both options are in effect for the file system. The root of the problem is some bad logic in the xfs_showargs() function, which is used to format the file system type-specific options in effect for a file system. The problem originated in this GIT commit: Move platform specific mount option parse out of core XFS code Date: 11/22/07 Author: Dave Chinner SHA1 ID: a67d7c5f5d25d0b13a4dfb182697135b014fa478 For XFS quotas, project and group quota management are mutually exclusive--only one can be in effect at a time. There are two parts to managing quotas: aggregating usage information; and enforcing limits. It is possible to have a quota in effect (aggregating usage) but not enforced. These features are recorded on an XFS mount point using these flags: XFS_PQUOTA_ACCT - Project quotas are aggregated XFS_GQUOTA_ACCT - Group quotas are aggregated XFS_OQUOTA_ENFD - Project/group quotas are enforced The code in error is in fs/xfs/linux-2.6/xfs_super.c: if (mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_PRJQUOTA); else if (mp->m_qflags & XFS_PQUOTA_ACCT) seq_puts(m, "," MNTOPT_PQUOTANOENF); if (mp->m_qflags & (XFS_GQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_GRPQUOTA); else if (mp->m_qflags & XFS_GQUOTA_ACCT) seq_puts(m, "," MNTOPT_GQUOTANOENF); The problem is that XFS_OQUOTA_ENFD will be set in mp->m_qflags if either group or project quotas are enforced, and as a result both MNTOPT_PRJQUOTA and MNTOPT_GRPQUOTA will be shown as mount options. Signed-off-by: Alex Elder <aelder@sgi.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Felix Blyakher <felixb@sgi.com>
2009-09-03 06:02:24 +08:00
else
seq_puts(m, ",gqnoenforce");
xfs: xfs_showargs() reports group *and* project quotas enabled If you enable group or project quotas on an XFS file system, then the mount table presented through /proc/self/mounts erroneously shows that both options are in effect for the file system. The root of the problem is some bad logic in the xfs_showargs() function, which is used to format the file system type-specific options in effect for a file system. The problem originated in this GIT commit: Move platform specific mount option parse out of core XFS code Date: 11/22/07 Author: Dave Chinner SHA1 ID: a67d7c5f5d25d0b13a4dfb182697135b014fa478 For XFS quotas, project and group quota management are mutually exclusive--only one can be in effect at a time. There are two parts to managing quotas: aggregating usage information; and enforcing limits. It is possible to have a quota in effect (aggregating usage) but not enforced. These features are recorded on an XFS mount point using these flags: XFS_PQUOTA_ACCT - Project quotas are aggregated XFS_GQUOTA_ACCT - Group quotas are aggregated XFS_OQUOTA_ENFD - Project/group quotas are enforced The code in error is in fs/xfs/linux-2.6/xfs_super.c: if (mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_PRJQUOTA); else if (mp->m_qflags & XFS_PQUOTA_ACCT) seq_puts(m, "," MNTOPT_PQUOTANOENF); if (mp->m_qflags & (XFS_GQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_GRPQUOTA); else if (mp->m_qflags & XFS_GQUOTA_ACCT) seq_puts(m, "," MNTOPT_GQUOTANOENF); The problem is that XFS_OQUOTA_ENFD will be set in mp->m_qflags if either group or project quotas are enforced, and as a result both MNTOPT_PRJQUOTA and MNTOPT_GRPQUOTA will be shown as mount options. Signed-off-by: Alex Elder <aelder@sgi.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Felix Blyakher <felixb@sgi.com>
2009-09-03 06:02:24 +08:00
}
if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT))
seq_puts(m, ",noquota");
return 0;
}
__uint64_t
xfs_max_file_offset(
unsigned int blockshift)
{
unsigned int pagefactor = 1;
unsigned int bitshift = BITS_PER_LONG - 1;
/* Figure out maximum filesize, on Linux this can depend on
* the filesystem blocksize (on 32 bit platforms).
* __block_write_begin does this in an [unsigned] long...
* page->index << (PAGE_SHIFT - bbits)
* So, for page sized blocks (4K on 32 bit platforms),
* this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is
* (((u64)PAGE_SIZE << (BITS_PER_LONG-1))-1)
* but for smaller blocksizes it is less (bbits = log2 bsize).
* Note1: get_block_t takes a long (implicit cast from above)
* Note2: The Large Block Device (LBD and HAVE_SECTOR_T) patch
* can optionally convert the [unsigned] long from above into
* an [unsigned] long long.
*/
#if BITS_PER_LONG == 32
# if defined(CONFIG_LBDAF)
ASSERT(sizeof(sector_t) == 8);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
pagefactor = PAGE_SIZE;
bitshift = BITS_PER_LONG;
# else
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
pagefactor = PAGE_SIZE >> (PAGE_SHIFT - blockshift);
# endif
#endif
return (((__uint64_t)pagefactor) << bitshift) - 1;
}
/*
* Set parameters for inode allocation heuristics, taking into account
* filesystem size and inode32/inode64 mount options; i.e. specifically
* whether or not XFS_MOUNT_SMALL_INUMS is set.
*
* Inode allocation patterns are altered only if inode32 is requested
* (XFS_MOUNT_SMALL_INUMS), and the filesystem is sufficiently large.
* If altered, XFS_MOUNT_32BITINODES is set as well.
*
* An agcount independent of that in the mount structure is provided
* because in the growfs case, mp->m_sb.sb_agcount is not yet updated
* to the potentially higher ag count.
*
* Returns the maximum AG index which may contain inodes.
*/
xfs_agnumber_t
xfs_set_inode_alloc(
struct xfs_mount *mp,
xfs_agnumber_t agcount)
{
xfs_agnumber_t index;
xfs_agnumber_t maxagi = 0;
xfs_sb_t *sbp = &mp->m_sb;
xfs_agnumber_t max_metadata;
xfs_agino_t agino;
xfs_ino_t ino;
/*
* Calculate how much should be reserved for inodes to meet
* the max inode percentage. Used only for inode32.
*/
if (mp->m_maxicount) {
__uint64_t icount;
icount = sbp->sb_dblocks * sbp->sb_imax_pct;
do_div(icount, 100);
icount += sbp->sb_agblocks - 1;
do_div(icount, sbp->sb_agblocks);
max_metadata = icount;
} else {
max_metadata = agcount;
}
/* Get the last possible inode in the filesystem */
agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
/*
* If user asked for no more than 32-bit inodes, and the fs is
* sufficiently large, set XFS_MOUNT_32BITINODES if we must alter
* the allocator to accommodate the request.
*/
if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) && ino > XFS_MAXINUMBER_32)
mp->m_flags |= XFS_MOUNT_32BITINODES;
else
mp->m_flags &= ~XFS_MOUNT_32BITINODES;
for (index = 0; index < agcount; index++) {
struct xfs_perag *pag;
ino = XFS_AGINO_TO_INO(mp, index, agino);
pag = xfs_perag_get(mp, index);
if (mp->m_flags & XFS_MOUNT_32BITINODES) {
if (ino > XFS_MAXINUMBER_32) {
pag->pagi_inodeok = 0;
pag->pagf_metadata = 0;
} else {
pag->pagi_inodeok = 1;
maxagi++;
if (index < max_metadata)
pag->pagf_metadata = 1;
else
pag->pagf_metadata = 0;
}
} else {
pag->pagi_inodeok = 1;
pag->pagf_metadata = 0;
}
xfs_perag_put(pag);
}
return (mp->m_flags & XFS_MOUNT_32BITINODES) ? maxagi : agcount;
}
STATIC int
xfs_blkdev_get(
xfs_mount_t *mp,
const char *name,
struct block_device **bdevp)
{
int error = 0;
*bdevp = blkdev_get_by_path(name, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
mp);
if (IS_ERR(*bdevp)) {
error = PTR_ERR(*bdevp);
xfs_warn(mp, "Invalid device [%s], error=%d", name, error);
}
return error;
}
STATIC void
xfs_blkdev_put(
struct block_device *bdev)
{
if (bdev)
block: make blkdev_get/put() handle exclusive access Over time, block layer has accumulated a set of APIs dealing with bdev open, close, claim and release. * blkdev_get/put() are the primary open and close functions. * bd_claim/release() deal with exclusive open. * open/close_bdev_exclusive() are combination of open and claim and the other way around, respectively. * bd_link/unlink_disk_holder() to create and remove holder/slave symlinks. * open_by_devnum() wraps bdget() + blkdev_get(). The interface is a bit confusing and the decoupling of open and claim makes it impossible to properly guarantee exclusive access as in-kernel open + claim sequence can disturb the existing exclusive open even before the block layer knows the current open if for another exclusive access. Reorganize the interface such that, * blkdev_get() is extended to include exclusive access management. @holder argument is added and, if is @FMODE_EXCL specified, it will gain exclusive access atomically w.r.t. other exclusive accesses. * blkdev_put() is similarly extended. It now takes @mode argument and if @FMODE_EXCL is set, it releases an exclusive access. Also, when the last exclusive claim is released, the holder/slave symlinks are removed automatically. * bd_claim/release() and close_bdev_exclusive() are no longer necessary and either made static or removed. * bd_link_disk_holder() remains the same but bd_unlink_disk_holder() is no longer necessary and removed. * open_bdev_exclusive() becomes a simple wrapper around lookup_bdev() and blkdev_get(). It also has an unexpected extra bdev_read_only() test which probably should be moved into blkdev_get(). * open_by_devnum() is modified to take @holder argument and pass it to blkdev_get(). Most of bdev open/close operations are unified into blkdev_get/put() and most exclusive accesses are tested atomically at the open time (as it should). This cleans up code and removes some, both valid and invalid, but unnecessary all the same, corner cases. open_bdev_exclusive() and open_by_devnum() can use further cleanup - rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop special features. Well, let's leave them for another day. Most conversions are straight-forward. drbd conversion is a bit more involved as there was some reordering, but the logic should stay the same. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Brown <neilb@suse.de> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Acked-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Philipp Reisner <philipp.reisner@linbit.com> Cc: Peter Osterlund <petero2@telia.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Alex Elder <aelder@sgi.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: dm-devel@redhat.com Cc: drbd-dev@lists.linbit.com Cc: Leo Chen <leochen@broadcom.com> Cc: Scott Branden <sbranden@broadcom.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Joern Engel <joern@logfs.org> Cc: reiserfs-devel@vger.kernel.org Cc: Alexander Viro <viro@zeniv.linux.org.uk>
2010-11-13 18:55:17 +08:00
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
void
xfs_blkdev_issue_flush(
xfs_buftarg_t *buftarg)
{
blkdev_issue_flush(buftarg->bt_bdev, GFP_NOFS, NULL);
}
STATIC void
xfs_close_devices(
struct xfs_mount *mp)
{
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
xfs_free_buftarg(mp, mp->m_logdev_targp);
xfs_blkdev_put(logdev);
}
if (mp->m_rtdev_targp) {
struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
xfs_free_buftarg(mp, mp->m_rtdev_targp);
xfs_blkdev_put(rtdev);
}
xfs_free_buftarg(mp, mp->m_ddev_targp);
}
/*
* The file system configurations are:
* (1) device (partition) with data and internal log
* (2) logical volume with data and log subvolumes.
* (3) logical volume with data, log, and realtime subvolumes.
*
* We only have to handle opening the log and realtime volumes here if
* they are present. The data subvolume has already been opened by
* get_sb_bdev() and is stored in sb->s_bdev.
*/
STATIC int
xfs_open_devices(
struct xfs_mount *mp)
{
struct block_device *ddev = mp->m_super->s_bdev;
struct block_device *logdev = NULL, *rtdev = NULL;
int error;
/*
* Open real time and log devices - order is important.
*/
if (mp->m_logname) {
error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
if (error)
goto out;
}
if (mp->m_rtname) {
error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev);
if (error)
goto out_close_logdev;
if (rtdev == ddev || rtdev == logdev) {
xfs_warn(mp,
"Cannot mount filesystem with identical rtdev and ddev/logdev.");
error = -EINVAL;
goto out_close_rtdev;
}
}
/*
* Setup xfs_mount buffer target pointers
*/
error = -ENOMEM;
mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev);
if (!mp->m_ddev_targp)
goto out_close_rtdev;
if (rtdev) {
mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev);
if (!mp->m_rtdev_targp)
goto out_free_ddev_targ;
}
if (logdev && logdev != ddev) {
mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev);
if (!mp->m_logdev_targp)
goto out_free_rtdev_targ;
} else {
mp->m_logdev_targp = mp->m_ddev_targp;
}
return 0;
out_free_rtdev_targ:
if (mp->m_rtdev_targp)
xfs_free_buftarg(mp, mp->m_rtdev_targp);
out_free_ddev_targ:
xfs_free_buftarg(mp, mp->m_ddev_targp);
out_close_rtdev:
xfs_blkdev_put(rtdev);
out_close_logdev:
if (logdev && logdev != ddev)
xfs_blkdev_put(logdev);
out:
return error;
}
/*
* Setup xfs_mount buffer target pointers based on superblock
*/
STATIC int
xfs_setup_devices(
struct xfs_mount *mp)
{
int error;
error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_sectsize);
if (error)
return error;
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
unsigned int log_sector_size = BBSIZE;
if (xfs_sb_version_hassector(&mp->m_sb))
log_sector_size = mp->m_sb.sb_logsectsize;
error = xfs_setsize_buftarg(mp->m_logdev_targp,
log_sector_size);
if (error)
return error;
}
if (mp->m_rtdev_targp) {
error = xfs_setsize_buftarg(mp->m_rtdev_targp,
mp->m_sb.sb_sectsize);
if (error)
return error;
}
return 0;
}
STATIC int
xfs_init_mount_workqueues(
struct xfs_mount *mp)
{
xfs: replace global xfslogd wq with per-mount wq The xfslogd workqueue is a global, single-job workqueue for buffer ioend processing. This means we allow for a single work item at a time for all possible XFS mounts on a system. fsstress testing in loopback XFS over XFS configurations has reproduced xfslogd deadlocks due to the single threaded nature of the queue and dependencies introduced between the separate XFS instances by online discard (-o discard). Discard over a loopback device converts the discard request to a hole punch (fallocate) on the underlying file. Online discard requests are issued synchronously and from xfslogd context in XFS, hence the xfslogd workqueue is blocked in the upper fs waiting on a hole punch request to be servied in the lower fs. If the lower fs issues I/O that depends on xfslogd to complete, both filesystems end up hung indefinitely. This is reproduced reliabily by generic/013 on XFS->loop->XFS test devices with the '-o discard' mount option. Further, docker implementations appear to use this kind of configuration for container instance filesystems by default (container fs->dm-> loop->base fs) and therefore are subject to this deadlock when running on XFS. Replace the global xfslogd workqueue with a per-mount variant. This guarantees each mount access to a single worker and prevents deadlocks due to inter-fs dependencies introduced by discard. Since the queue is only responsible for buffer iodone processing at this point in time, rename xfslogd to xfs-buf. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-11-28 10:59:58 +08:00
mp->m_buf_workqueue = alloc_workqueue("xfs-buf/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 1, mp->m_fsname);
xfs: replace global xfslogd wq with per-mount wq The xfslogd workqueue is a global, single-job workqueue for buffer ioend processing. This means we allow for a single work item at a time for all possible XFS mounts on a system. fsstress testing in loopback XFS over XFS configurations has reproduced xfslogd deadlocks due to the single threaded nature of the queue and dependencies introduced between the separate XFS instances by online discard (-o discard). Discard over a loopback device converts the discard request to a hole punch (fallocate) on the underlying file. Online discard requests are issued synchronously and from xfslogd context in XFS, hence the xfslogd workqueue is blocked in the upper fs waiting on a hole punch request to be servied in the lower fs. If the lower fs issues I/O that depends on xfslogd to complete, both filesystems end up hung indefinitely. This is reproduced reliabily by generic/013 on XFS->loop->XFS test devices with the '-o discard' mount option. Further, docker implementations appear to use this kind of configuration for container instance filesystems by default (container fs->dm-> loop->base fs) and therefore are subject to this deadlock when running on XFS. Replace the global xfslogd workqueue with a per-mount variant. This guarantees each mount access to a single worker and prevents deadlocks due to inter-fs dependencies introduced by discard. Since the queue is only responsible for buffer iodone processing at this point in time, rename xfslogd to xfs-buf. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-11-28 10:59:58 +08:00
if (!mp->m_buf_workqueue)
goto out;
mp->m_data_workqueue = alloc_workqueue("xfs-data/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
if (!mp->m_data_workqueue)
xfs: replace global xfslogd wq with per-mount wq The xfslogd workqueue is a global, single-job workqueue for buffer ioend processing. This means we allow for a single work item at a time for all possible XFS mounts on a system. fsstress testing in loopback XFS over XFS configurations has reproduced xfslogd deadlocks due to the single threaded nature of the queue and dependencies introduced between the separate XFS instances by online discard (-o discard). Discard over a loopback device converts the discard request to a hole punch (fallocate) on the underlying file. Online discard requests are issued synchronously and from xfslogd context in XFS, hence the xfslogd workqueue is blocked in the upper fs waiting on a hole punch request to be servied in the lower fs. If the lower fs issues I/O that depends on xfslogd to complete, both filesystems end up hung indefinitely. This is reproduced reliabily by generic/013 on XFS->loop->XFS test devices with the '-o discard' mount option. Further, docker implementations appear to use this kind of configuration for container instance filesystems by default (container fs->dm-> loop->base fs) and therefore are subject to this deadlock when running on XFS. Replace the global xfslogd workqueue with a per-mount variant. This guarantees each mount access to a single worker and prevents deadlocks due to inter-fs dependencies introduced by discard. Since the queue is only responsible for buffer iodone processing at this point in time, rename xfslogd to xfs-buf. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-11-28 10:59:58 +08:00
goto out_destroy_buf;
mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
if (!mp->m_unwritten_workqueue)
goto out_destroy_data_iodone_queue;
mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
if (!mp->m_cil_workqueue)
goto out_destroy_unwritten;
mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
xfs: give all workqueues rescuer threads We're consistently hitting deadlocks here with XFS on recent kernels. After some digging through the crash files, it looks like everyone in the system is waiting for XFS to reclaim memory. Something like this: PID: 2733434 TASK: ffff8808cd242800 CPU: 19 COMMAND: "java" #0 [ffff880019c53588] __schedule at ffffffff818c4df2 #1 [ffff880019c535d8] schedule at ffffffff818c5517 #2 [ffff880019c535f8] _xfs_log_force_lsn at ffffffff81316348 #3 [ffff880019c53688] xfs_log_force_lsn at ffffffff813164fb #4 [ffff880019c536b8] xfs_iunpin_wait at ffffffff8130835e #5 [ffff880019c53728] xfs_reclaim_inode at ffffffff812fd453 #6 [ffff880019c53778] xfs_reclaim_inodes_ag at ffffffff812fd8c7 #7 [ffff880019c53928] xfs_reclaim_inodes_nr at ffffffff812fe433 #8 [ffff880019c53958] xfs_fs_free_cached_objects at ffffffff8130d3b9 #9 [ffff880019c53968] super_cache_scan at ffffffff811a6f73 #10 [ffff880019c539c8] shrink_slab at ffffffff811460e6 #11 [ffff880019c53aa8] shrink_zone at ffffffff8114a53f #12 [ffff880019c53b48] do_try_to_free_pages at ffffffff8114a8ba #13 [ffff880019c53be8] try_to_free_pages at ffffffff8114ad5a #14 [ffff880019c53c78] __alloc_pages_nodemask at ffffffff8113e1b8 #15 [ffff880019c53d88] alloc_kmem_pages_node at ffffffff8113e671 #16 [ffff880019c53dd8] copy_process at ffffffff8104f781 #17 [ffff880019c53ec8] do_fork at ffffffff8105129c #18 [ffff880019c53f38] sys_clone at ffffffff810515b6 #19 [ffff880019c53f48] stub_clone at ffffffff818c8e4d xfs_log_force_lsn is waiting for logs to get cleaned, which is waiting for IO, which is waiting for workers to complete the IO which is waiting for worker threads that don't exist yet: PID: 2752451 TASK: ffff880bd6bdda00 CPU: 37 COMMAND: "kworker/37:1" #0 [ffff8808d20abbb0] __schedule at ffffffff818c4df2 #1 [ffff8808d20abc00] schedule at ffffffff818c5517 #2 [ffff8808d20abc20] schedule_timeout at ffffffff818c7c6c #3 [ffff8808d20abcc0] wait_for_completion_killable at ffffffff818c6495 #4 [ffff8808d20abd30] kthread_create_on_node at ffffffff8106ec82 #5 [ffff8808d20abdf0] create_worker at ffffffff8106752f #6 [ffff8808d20abe40] worker_thread at ffffffff810699be #7 [ffff8808d20abec0] kthread at ffffffff8106ef59 #8 [ffff8808d20abf50] ret_from_fork at ffffffff818c8ac8 I think we should be using WQ_MEM_RECLAIM to make sure this thread pool makes progress when we're not able to allocate new workers. [dchinner: make all workqueues WQ_MEM_RECLAIM] Signed-off-by: Chris Mason <clm@fb.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-11-10 07:10:34 +08:00
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
if (!mp->m_reclaim_workqueue)
goto out_destroy_cil;
mp->m_log_workqueue = alloc_workqueue("xfs-log/%s",
xfs: give all workqueues rescuer threads We're consistently hitting deadlocks here with XFS on recent kernels. After some digging through the crash files, it looks like everyone in the system is waiting for XFS to reclaim memory. Something like this: PID: 2733434 TASK: ffff8808cd242800 CPU: 19 COMMAND: "java" #0 [ffff880019c53588] __schedule at ffffffff818c4df2 #1 [ffff880019c535d8] schedule at ffffffff818c5517 #2 [ffff880019c535f8] _xfs_log_force_lsn at ffffffff81316348 #3 [ffff880019c53688] xfs_log_force_lsn at ffffffff813164fb #4 [ffff880019c536b8] xfs_iunpin_wait at ffffffff8130835e #5 [ffff880019c53728] xfs_reclaim_inode at ffffffff812fd453 #6 [ffff880019c53778] xfs_reclaim_inodes_ag at ffffffff812fd8c7 #7 [ffff880019c53928] xfs_reclaim_inodes_nr at ffffffff812fe433 #8 [ffff880019c53958] xfs_fs_free_cached_objects at ffffffff8130d3b9 #9 [ffff880019c53968] super_cache_scan at ffffffff811a6f73 #10 [ffff880019c539c8] shrink_slab at ffffffff811460e6 #11 [ffff880019c53aa8] shrink_zone at ffffffff8114a53f #12 [ffff880019c53b48] do_try_to_free_pages at ffffffff8114a8ba #13 [ffff880019c53be8] try_to_free_pages at ffffffff8114ad5a #14 [ffff880019c53c78] __alloc_pages_nodemask at ffffffff8113e1b8 #15 [ffff880019c53d88] alloc_kmem_pages_node at ffffffff8113e671 #16 [ffff880019c53dd8] copy_process at ffffffff8104f781 #17 [ffff880019c53ec8] do_fork at ffffffff8105129c #18 [ffff880019c53f38] sys_clone at ffffffff810515b6 #19 [ffff880019c53f48] stub_clone at ffffffff818c8e4d xfs_log_force_lsn is waiting for logs to get cleaned, which is waiting for IO, which is waiting for workers to complete the IO which is waiting for worker threads that don't exist yet: PID: 2752451 TASK: ffff880bd6bdda00 CPU: 37 COMMAND: "kworker/37:1" #0 [ffff8808d20abbb0] __schedule at ffffffff818c4df2 #1 [ffff8808d20abc00] schedule at ffffffff818c5517 #2 [ffff8808d20abc20] schedule_timeout at ffffffff818c7c6c #3 [ffff8808d20abcc0] wait_for_completion_killable at ffffffff818c6495 #4 [ffff8808d20abd30] kthread_create_on_node at ffffffff8106ec82 #5 [ffff8808d20abdf0] create_worker at ffffffff8106752f #6 [ffff8808d20abe40] worker_thread at ffffffff810699be #7 [ffff8808d20abec0] kthread at ffffffff8106ef59 #8 [ffff8808d20abf50] ret_from_fork at ffffffff818c8ac8 I think we should be using WQ_MEM_RECLAIM to make sure this thread pool makes progress when we're not able to allocate new workers. [dchinner: make all workqueues WQ_MEM_RECLAIM] Signed-off-by: Chris Mason <clm@fb.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-11-10 07:10:34 +08:00
WQ_MEM_RECLAIM|WQ_FREEZABLE|WQ_HIGHPRI, 0,
mp->m_fsname);
if (!mp->m_log_workqueue)
goto out_destroy_reclaim;
mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s",
xfs: give all workqueues rescuer threads We're consistently hitting deadlocks here with XFS on recent kernels. After some digging through the crash files, it looks like everyone in the system is waiting for XFS to reclaim memory. Something like this: PID: 2733434 TASK: ffff8808cd242800 CPU: 19 COMMAND: "java" #0 [ffff880019c53588] __schedule at ffffffff818c4df2 #1 [ffff880019c535d8] schedule at ffffffff818c5517 #2 [ffff880019c535f8] _xfs_log_force_lsn at ffffffff81316348 #3 [ffff880019c53688] xfs_log_force_lsn at ffffffff813164fb #4 [ffff880019c536b8] xfs_iunpin_wait at ffffffff8130835e #5 [ffff880019c53728] xfs_reclaim_inode at ffffffff812fd453 #6 [ffff880019c53778] xfs_reclaim_inodes_ag at ffffffff812fd8c7 #7 [ffff880019c53928] xfs_reclaim_inodes_nr at ffffffff812fe433 #8 [ffff880019c53958] xfs_fs_free_cached_objects at ffffffff8130d3b9 #9 [ffff880019c53968] super_cache_scan at ffffffff811a6f73 #10 [ffff880019c539c8] shrink_slab at ffffffff811460e6 #11 [ffff880019c53aa8] shrink_zone at ffffffff8114a53f #12 [ffff880019c53b48] do_try_to_free_pages at ffffffff8114a8ba #13 [ffff880019c53be8] try_to_free_pages at ffffffff8114ad5a #14 [ffff880019c53c78] __alloc_pages_nodemask at ffffffff8113e1b8 #15 [ffff880019c53d88] alloc_kmem_pages_node at ffffffff8113e671 #16 [ffff880019c53dd8] copy_process at ffffffff8104f781 #17 [ffff880019c53ec8] do_fork at ffffffff8105129c #18 [ffff880019c53f38] sys_clone at ffffffff810515b6 #19 [ffff880019c53f48] stub_clone at ffffffff818c8e4d xfs_log_force_lsn is waiting for logs to get cleaned, which is waiting for IO, which is waiting for workers to complete the IO which is waiting for worker threads that don't exist yet: PID: 2752451 TASK: ffff880bd6bdda00 CPU: 37 COMMAND: "kworker/37:1" #0 [ffff8808d20abbb0] __schedule at ffffffff818c4df2 #1 [ffff8808d20abc00] schedule at ffffffff818c5517 #2 [ffff8808d20abc20] schedule_timeout at ffffffff818c7c6c #3 [ffff8808d20abcc0] wait_for_completion_killable at ffffffff818c6495 #4 [ffff8808d20abd30] kthread_create_on_node at ffffffff8106ec82 #5 [ffff8808d20abdf0] create_worker at ffffffff8106752f #6 [ffff8808d20abe40] worker_thread at ffffffff810699be #7 [ffff8808d20abec0] kthread at ffffffff8106ef59 #8 [ffff8808d20abf50] ret_from_fork at ffffffff818c8ac8 I think we should be using WQ_MEM_RECLAIM to make sure this thread pool makes progress when we're not able to allocate new workers. [dchinner: make all workqueues WQ_MEM_RECLAIM] Signed-off-by: Chris Mason <clm@fb.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-11-10 07:10:34 +08:00
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
if (!mp->m_eofblocks_workqueue)
goto out_destroy_log;
return 0;
out_destroy_log:
destroy_workqueue(mp->m_log_workqueue);
out_destroy_reclaim:
destroy_workqueue(mp->m_reclaim_workqueue);
out_destroy_cil:
destroy_workqueue(mp->m_cil_workqueue);
out_destroy_unwritten:
destroy_workqueue(mp->m_unwritten_workqueue);
out_destroy_data_iodone_queue:
destroy_workqueue(mp->m_data_workqueue);
xfs: replace global xfslogd wq with per-mount wq The xfslogd workqueue is a global, single-job workqueue for buffer ioend processing. This means we allow for a single work item at a time for all possible XFS mounts on a system. fsstress testing in loopback XFS over XFS configurations has reproduced xfslogd deadlocks due to the single threaded nature of the queue and dependencies introduced between the separate XFS instances by online discard (-o discard). Discard over a loopback device converts the discard request to a hole punch (fallocate) on the underlying file. Online discard requests are issued synchronously and from xfslogd context in XFS, hence the xfslogd workqueue is blocked in the upper fs waiting on a hole punch request to be servied in the lower fs. If the lower fs issues I/O that depends on xfslogd to complete, both filesystems end up hung indefinitely. This is reproduced reliabily by generic/013 on XFS->loop->XFS test devices with the '-o discard' mount option. Further, docker implementations appear to use this kind of configuration for container instance filesystems by default (container fs->dm-> loop->base fs) and therefore are subject to this deadlock when running on XFS. Replace the global xfslogd workqueue with a per-mount variant. This guarantees each mount access to a single worker and prevents deadlocks due to inter-fs dependencies introduced by discard. Since the queue is only responsible for buffer iodone processing at this point in time, rename xfslogd to xfs-buf. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-11-28 10:59:58 +08:00
out_destroy_buf:
destroy_workqueue(mp->m_buf_workqueue);
out:
return -ENOMEM;
}
STATIC void
xfs_destroy_mount_workqueues(
struct xfs_mount *mp)
{
destroy_workqueue(mp->m_eofblocks_workqueue);
destroy_workqueue(mp->m_log_workqueue);
destroy_workqueue(mp->m_reclaim_workqueue);
destroy_workqueue(mp->m_cil_workqueue);
destroy_workqueue(mp->m_data_workqueue);
destroy_workqueue(mp->m_unwritten_workqueue);
xfs: replace global xfslogd wq with per-mount wq The xfslogd workqueue is a global, single-job workqueue for buffer ioend processing. This means we allow for a single work item at a time for all possible XFS mounts on a system. fsstress testing in loopback XFS over XFS configurations has reproduced xfslogd deadlocks due to the single threaded nature of the queue and dependencies introduced between the separate XFS instances by online discard (-o discard). Discard over a loopback device converts the discard request to a hole punch (fallocate) on the underlying file. Online discard requests are issued synchronously and from xfslogd context in XFS, hence the xfslogd workqueue is blocked in the upper fs waiting on a hole punch request to be servied in the lower fs. If the lower fs issues I/O that depends on xfslogd to complete, both filesystems end up hung indefinitely. This is reproduced reliabily by generic/013 on XFS->loop->XFS test devices with the '-o discard' mount option. Further, docker implementations appear to use this kind of configuration for container instance filesystems by default (container fs->dm-> loop->base fs) and therefore are subject to this deadlock when running on XFS. Replace the global xfslogd workqueue with a per-mount variant. This guarantees each mount access to a single worker and prevents deadlocks due to inter-fs dependencies introduced by discard. Since the queue is only responsible for buffer iodone processing at this point in time, rename xfslogd to xfs-buf. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-11-28 10:59:58 +08:00
destroy_workqueue(mp->m_buf_workqueue);
}
xfs: xfs_sync_data is redundant. We don't do any data writeback from XFS any more - the VFS is completely responsible for that, including for freeze. We can replace the remaining caller with a VFS level function that achieves the same thing, but without conflicting with current writeback work. This means we can remove the flush_work and xfs_flush_inodes() - the VFS functionality completely replaces the internal flush queue for doing this writeback work in a separate context to avoid stack overruns. This does have one complication - it cannot be called with page locks held. Hence move the flushing of delalloc space when ENOSPC occurs back up into xfs_file_aio_buffered_write when we don't hold any locks that will stall writeback. Unfortunately, writeback_inodes_sb_if_idle() is not sufficient to trigger delalloc conversion fast enough to prevent spurious ENOSPC whent here are hundreds of writers, thousands of small files and GBs of free RAM. Hence we need to use sync_sb_inodes() to block callers while we wait for writeback like the previous xfs_flush_inodes implementation did. That means we have to hold the s_umount lock here, but because this call can nest inside i_mutex (the parent directory in the create case, held by the VFS), we have to use down_read_trylock() to avoid potential deadlocks. In practice, this trylock will succeed on almost every attempt as unmount/remount type operations are exceedingly rare. Note: we always need to pass a count of zero to generic_file_buffered_write() as the previously written byte count. We only do this by accident before this patch by the virtue of ret always being zero when there are no errors. Make this explicit rather than needing to specifically zero ret in the ENOSPC retry case. Signed-off-by: Dave Chinner <dchinner@redhat.com> Tested-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-10-08 18:56:04 +08:00
/*
* Flush all dirty data to disk. Must not be called while holding an XFS_ILOCK
* or a page lock. We use sync_inodes_sb() here to ensure we block while waiting
* for IO to complete so that we effectively throttle multiple callers to the
* rate at which IO is completing.
*/
void
xfs_flush_inodes(
struct xfs_mount *mp)
{
struct super_block *sb = mp->m_super;
if (down_read_trylock(&sb->s_umount)) {
sync_inodes_sb(sb);
xfs: xfs_sync_data is redundant. We don't do any data writeback from XFS any more - the VFS is completely responsible for that, including for freeze. We can replace the remaining caller with a VFS level function that achieves the same thing, but without conflicting with current writeback work. This means we can remove the flush_work and xfs_flush_inodes() - the VFS functionality completely replaces the internal flush queue for doing this writeback work in a separate context to avoid stack overruns. This does have one complication - it cannot be called with page locks held. Hence move the flushing of delalloc space when ENOSPC occurs back up into xfs_file_aio_buffered_write when we don't hold any locks that will stall writeback. Unfortunately, writeback_inodes_sb_if_idle() is not sufficient to trigger delalloc conversion fast enough to prevent spurious ENOSPC whent here are hundreds of writers, thousands of small files and GBs of free RAM. Hence we need to use sync_sb_inodes() to block callers while we wait for writeback like the previous xfs_flush_inodes implementation did. That means we have to hold the s_umount lock here, but because this call can nest inside i_mutex (the parent directory in the create case, held by the VFS), we have to use down_read_trylock() to avoid potential deadlocks. In practice, this trylock will succeed on almost every attempt as unmount/remount type operations are exceedingly rare. Note: we always need to pass a count of zero to generic_file_buffered_write() as the previously written byte count. We only do this by accident before this patch by the virtue of ret always being zero when there are no errors. Make this explicit rather than needing to specifically zero ret in the ENOSPC retry case. Signed-off-by: Dave Chinner <dchinner@redhat.com> Tested-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-10-08 18:56:04 +08:00
up_read(&sb->s_umount);
}
}
/* Catch misguided souls that try to use this interface on XFS */
STATIC struct inode *
xfs_fs_alloc_inode(
struct super_block *sb)
{
BUG();
return NULL;
}
/*
* Now that the generic code is guaranteed not to be accessing
xfs: remove xfs_fs_evict_inode() Joe Lawrence reported a list_add corruption with 4.6-rc1 when testing some custom md administration code that made it's own block device nodes for the md array. The simple test loop of: for i in {0..100}; do mknod --mode=0600 $tmp/tmp_node b $MAJOR $MINOR mdadm --detail --export $tmp/tmp_node > /dev/null rm -f $tmp/tmp_node done Would produce this warning in bd_acquire() when mdadm opened the device node: list_add double add: new=ffff88043831c7b8, prev=ffff8804380287d8, next=ffff88043831c7b8. And then produce this from bd_forget from kdevtmpfs evicting a block dev inode: list_del corruption. prev->next should be ffff8800bb83eb10, but was ffff88043831c7b8 This is a regression caused by commit c19b3b05 ("xfs: mode di_mode to vfs inode"). The issue is that xfs_inactive() frees the unlinked inode, and the above commit meant that this freeing zeroed the mode in the struct inode. The problem is that after evict() has called ->evict_inode, it expects the i_mode to be intact so that it can call bd_forget() or cd_forget() to drop the reference to the block device inode attached to the XFS inode. In reality, the only thing we do in xfs_fs_evict_inode() that is not generic is call xfs_inactive(). We can move the xfs_inactive() call to xfs_fs_destroy_inode() without any problems at all, and this will leave the VFS inode intact until it is completely done with it. So, remove xfs_fs_evict_inode(), and do the work it used to do in ->destroy_inode instead. cc: <stable@vger.kernel.org> # 4.6 Reported-by: Joe Lawrence <joe.lawrence@stratus.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-05-18 11:52:42 +08:00
* the linux inode, we can inactivate and reclaim the inode.
*/
STATIC void
xfs_fs_destroy_inode(
struct inode *inode)
{
struct xfs_inode *ip = XFS_I(inode);
trace_xfs_destroy_inode(ip);
xfs: remove xfs_fs_evict_inode() Joe Lawrence reported a list_add corruption with 4.6-rc1 when testing some custom md administration code that made it's own block device nodes for the md array. The simple test loop of: for i in {0..100}; do mknod --mode=0600 $tmp/tmp_node b $MAJOR $MINOR mdadm --detail --export $tmp/tmp_node > /dev/null rm -f $tmp/tmp_node done Would produce this warning in bd_acquire() when mdadm opened the device node: list_add double add: new=ffff88043831c7b8, prev=ffff8804380287d8, next=ffff88043831c7b8. And then produce this from bd_forget from kdevtmpfs evicting a block dev inode: list_del corruption. prev->next should be ffff8800bb83eb10, but was ffff88043831c7b8 This is a regression caused by commit c19b3b05 ("xfs: mode di_mode to vfs inode"). The issue is that xfs_inactive() frees the unlinked inode, and the above commit meant that this freeing zeroed the mode in the struct inode. The problem is that after evict() has called ->evict_inode, it expects the i_mode to be intact so that it can call bd_forget() or cd_forget() to drop the reference to the block device inode attached to the XFS inode. In reality, the only thing we do in xfs_fs_evict_inode() that is not generic is call xfs_inactive(). We can move the xfs_inactive() call to xfs_fs_destroy_inode() without any problems at all, and this will leave the VFS inode intact until it is completely done with it. So, remove xfs_fs_evict_inode(), and do the work it used to do in ->destroy_inode instead. cc: <stable@vger.kernel.org> # 4.6 Reported-by: Joe Lawrence <joe.lawrence@stratus.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-05-18 11:52:42 +08:00
ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
XFS_STATS_INC(ip->i_mount, vn_rele);
XFS_STATS_INC(ip->i_mount, vn_remove);
xfs_inactive(ip);
ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
xfs: remove xfs_fs_evict_inode() Joe Lawrence reported a list_add corruption with 4.6-rc1 when testing some custom md administration code that made it's own block device nodes for the md array. The simple test loop of: for i in {0..100}; do mknod --mode=0600 $tmp/tmp_node b $MAJOR $MINOR mdadm --detail --export $tmp/tmp_node > /dev/null rm -f $tmp/tmp_node done Would produce this warning in bd_acquire() when mdadm opened the device node: list_add double add: new=ffff88043831c7b8, prev=ffff8804380287d8, next=ffff88043831c7b8. And then produce this from bd_forget from kdevtmpfs evicting a block dev inode: list_del corruption. prev->next should be ffff8800bb83eb10, but was ffff88043831c7b8 This is a regression caused by commit c19b3b05 ("xfs: mode di_mode to vfs inode"). The issue is that xfs_inactive() frees the unlinked inode, and the above commit meant that this freeing zeroed the mode in the struct inode. The problem is that after evict() has called ->evict_inode, it expects the i_mode to be intact so that it can call bd_forget() or cd_forget() to drop the reference to the block device inode attached to the XFS inode. In reality, the only thing we do in xfs_fs_evict_inode() that is not generic is call xfs_inactive(). We can move the xfs_inactive() call to xfs_fs_destroy_inode() without any problems at all, and this will leave the VFS inode intact until it is completely done with it. So, remove xfs_fs_evict_inode(), and do the work it used to do in ->destroy_inode instead. cc: <stable@vger.kernel.org> # 4.6 Reported-by: Joe Lawrence <joe.lawrence@stratus.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-05-18 11:52:42 +08:00
XFS_STATS_INC(ip->i_mount, vn_reclaim);
/*
* We should never get here with one of the reclaim flags already set.
*/
ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIMABLE));
ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
/*
* We always use background reclaim here because even if the
* inode is clean, it still may be under IO and hence we have
* to take the flush lock. The background reclaim path handles
* this more efficiently than we can here, so simply let background
* reclaim tear down all inodes.
*/
xfs_inode_set_reclaim_tag(ip);
}
/*
* Slab object creation initialisation for the XFS inode.
* This covers only the idempotent fields in the XFS inode;
* all other fields need to be initialised on allocation
* from the slab. This avoids the need to repeatedly initialise
* fields in the xfs inode that left in the initialise state
* when freeing the inode.
*/
STATIC void
xfs_fs_inode_init_once(
void *inode)
{
struct xfs_inode *ip = inode;
memset(ip, 0, sizeof(struct xfs_inode));
/* vfs inode */
inode_init_once(VFS_I(ip));
/* xfs inode */
atomic_set(&ip->i_pincount, 0);
spin_lock_init(&ip->i_flags_lock);
mrlock_init(&ip->i_mmaplock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
"xfsino", ip->i_ino);
mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
"xfsino", ip->i_ino);
}
/*
* We do an unlocked check for XFS_IDONTCACHE here because we are already
* serialised against cache hits here via the inode->i_lock and igrab() in
* xfs_iget_cache_hit(). Hence a lookup that might clear this flag will not be
* racing with us, and it avoids needing to grab a spinlock here for every inode
* we drop the final reference on.
*/
STATIC int
xfs_fs_drop_inode(
struct inode *inode)
{
struct xfs_inode *ip = XFS_I(inode);
return generic_drop_inode(inode) || (ip->i_flags & XFS_IDONTCACHE);
}
STATIC void
xfs_free_fsname(
struct xfs_mount *mp)
{
kfree(mp->m_fsname);
kfree(mp->m_rtname);
kfree(mp->m_logname);
}
STATIC int
xfs_fs_sync_fs(
struct super_block *sb,
int wait)
{
struct xfs_mount *mp = XFS_M(sb);
/*
* Doing anything during the async pass would be counterproductive.
*/
if (!wait)
return 0;
xfs_log_force(mp, XFS_LOG_SYNC);
if (laptop_mode) {
/*
* The disk must be active because we're syncing.
* We schedule log work now (now that the disk is
* active) instead of later (when it might not be).
*/
flush_delayed_work(&mp->m_log->l_work);
}
return 0;
}
STATIC int
xfs_fs_statfs(
struct dentry *dentry,
struct kstatfs *statp)
{
struct xfs_mount *mp = XFS_M(dentry->d_sb);
xfs_sb_t *sbp = &mp->m_sb;
struct xfs_inode *ip = XFS_I(d_inode(dentry));
__uint64_t fakeinos, id;
__uint64_t icount;
__uint64_t ifree;
__uint64_t fdblocks;
xfs_extlen_t lsize;
__int64_t ffree;
statp->f_type = XFS_SB_MAGIC;
statp->f_namelen = MAXNAMELEN - 1;
id = huge_encode_dev(mp->m_ddev_targp->bt_dev);
statp->f_fsid.val[0] = (u32)id;
statp->f_fsid.val[1] = (u32)(id >> 32);
icount = percpu_counter_sum(&mp->m_icount);
ifree = percpu_counter_sum(&mp->m_ifree);
fdblocks = percpu_counter_sum(&mp->m_fdblocks);
spin_lock(&mp->m_sb_lock);
statp->f_bsize = sbp->sb_blocksize;
lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0;
statp->f_blocks = sbp->sb_dblocks - lsize;
spin_unlock(&mp->m_sb_lock);
statp->f_bfree = fdblocks - XFS_ALLOC_SET_ASIDE(mp);
statp->f_bavail = statp->f_bfree;
fakeinos = statp->f_bfree << sbp->sb_inopblog;
statp->f_files = MIN(icount + fakeinos, (__uint64_t)XFS_MAXINUMBER);
if (mp->m_maxicount)
statp->f_files = min_t(typeof(statp->f_files),
statp->f_files,
mp->m_maxicount);
/* If sb_icount overshot maxicount, report actual allocation */
statp->f_files = max_t(typeof(statp->f_files),
statp->f_files,
sbp->sb_icount);
/* make sure statp->f_ffree does not underflow */
ffree = statp->f_files - (icount - ifree);
statp->f_ffree = max_t(__int64_t, ffree, 0);
if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) ==
(XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))
xfs_qm_statvfs(ip, statp);
return 0;
}
STATIC void
xfs_save_resvblks(struct xfs_mount *mp)
{
__uint64_t resblks = 0;
mp->m_resblks_save = mp->m_resblks;
xfs_reserve_blocks(mp, &resblks, NULL);
}
STATIC void
xfs_restore_resvblks(struct xfs_mount *mp)
{
__uint64_t resblks;
if (mp->m_resblks_save) {
resblks = mp->m_resblks_save;
mp->m_resblks_save = 0;
} else
resblks = xfs_default_resblks(mp);
xfs_reserve_blocks(mp, &resblks, NULL);
}
/*
* Trigger writeback of all the dirty metadata in the file system.
*
* This ensures that the metadata is written to their location on disk rather
* than just existing in transactions in the log. This means after a quiesce
* there is no log replay required to write the inodes to disk - this is the
* primary difference between a sync and a quiesce.
*
* Note: xfs_log_quiesce() stops background log work - the callers must ensure
* it is started again when appropriate.
*/
static void
xfs_quiesce_attr(
struct xfs_mount *mp)
{
int error = 0;
/* wait for all modifications to complete */
while (atomic_read(&mp->m_active_trans) > 0)
delay(100);
/* force the log to unpin objects from the now complete transactions */
xfs_log_force(mp, XFS_LOG_SYNC);
/* reclaim inodes to do any IO before the freeze completes */
xfs_reclaim_inodes(mp, 0);
xfs_reclaim_inodes(mp, SYNC_WAIT);
/* Push the superblock and write an unmount record */
error = xfs_log_sbcount(mp);
if (error)
xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
"Frozen image may not be consistent.");
/*
* Just warn here till VFS can correctly support
* read-only remount without racing.
*/
WARN_ON(atomic_read(&mp->m_active_trans) != 0);
xfs_log_quiesce(mp);
}
STATIC int
xfs_test_remount_options(
struct super_block *sb,
struct xfs_mount *mp,
char *options)
{
int error = 0;
struct xfs_mount *tmp_mp;
tmp_mp = kmem_zalloc(sizeof(*tmp_mp), KM_MAYFAIL);
if (!tmp_mp)
return -ENOMEM;
tmp_mp->m_super = sb;
error = xfs_parseargs(tmp_mp, options);
xfs_free_fsname(tmp_mp);
kfree(tmp_mp);
return error;
}
STATIC int
xfs_fs_remount(
struct super_block *sb,
int *flags,
char *options)
{
struct xfs_mount *mp = XFS_M(sb);
xfs_sb_t *sbp = &mp->m_sb;
substring_t args[MAX_OPT_ARGS];
char *p;
int error;
/* First, check for complete junk; i.e. invalid options */
error = xfs_test_remount_options(sb, mp, options);
if (error)
return error;
fs: push sync_filesystem() down to the file system's remount_fs() Previously, the no-op "mount -o mount /dev/xxx" operation when the file system is already mounted read-write causes an implied, unconditional syncfs(). This seems pretty stupid, and it's certainly documented or guaraunteed to do this, nor is it particularly useful, except in the case where the file system was mounted rw and is getting remounted read-only. However, it's possible that there might be some file systems that are actually depending on this behavior. In most file systems, it's probably fine to only call sync_filesystem() when transitioning from read-write to read-only, and there are some file systems where this is not needed at all (for example, for a pseudo-filesystem or something like romfs). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: linux-fsdevel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Evgeniy Dushistov <dushistov@mail.ru> Cc: Jan Kara <jack@suse.cz> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Anders Larsen <al@alarsen.net> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: xfs@oss.sgi.com Cc: linux-btrfs@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: codalist@coda.cs.cmu.edu Cc: linux-ext4@vger.kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net Cc: fuse-devel@lists.sourceforge.net Cc: cluster-devel@redhat.com Cc: linux-mtd@lists.infradead.org Cc: jfs-discussion@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: linux-nilfs@vger.kernel.org Cc: linux-ntfs-dev@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Cc: reiserfs-devel@vger.kernel.org
2014-03-13 22:14:33 +08:00
sync_filesystem(sb);
while ((p = strsep(&options, ",")) != NULL) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_barrier:
mp->m_flags |= XFS_MOUNT_BARRIER;
break;
case Opt_nobarrier:
mp->m_flags &= ~XFS_MOUNT_BARRIER;
break;
case Opt_inode64:
mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
break;
case Opt_inode32:
mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
break;
default:
/*
* Logically we would return an error here to prevent
* users from believing they might have changed
* mount options using remount which can't be changed.
*
* But unfortunately mount(8) adds all options from
* mtab and fstab to the mount arguments in some cases
* so we can't blindly reject options, but have to
* check for each specified option if it actually
* differs from the currently set option and only
* reject it if that's the case.
*
* Until that is implemented we return success for
* every remount request, and silently ignore all
* options that we can't actually change.
*/
#if 0
xfs_info(mp,
"mount option \"%s\" not supported for remount", p);
return -EINVAL;
#else
break;
#endif
}
}
/* ro -> rw */
if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) {
if (mp->m_flags & XFS_MOUNT_NORECOVERY) {
xfs_warn(mp,
"ro->rw transition prohibited on norecovery mount");
return -EINVAL;
}
if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
xfs_sb_has_ro_compat_feature(sbp,
XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
xfs_warn(mp,
"ro->rw transition prohibited on unknown (0x%x) ro-compat filesystem",
(sbp->sb_features_ro_compat &
XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
return -EINVAL;
}
mp->m_flags &= ~XFS_MOUNT_RDONLY;
/*
* If this is the first remount to writeable state we
* might have some superblock changes to update.
*/
if (mp->m_update_sb) {
error = xfs_sync_sb(mp, false);
if (error) {
xfs_warn(mp, "failed to write sb changes");
return error;
}
mp->m_update_sb = false;
}
/*
* Fill out the reserve pool if it is empty. Use the stashed
* value if it is non-zero, otherwise go with the default.
*/
xfs_restore_resvblks(mp);
xfs_log_work_queue(mp);
}
/* rw -> ro */
if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) {
/*
* Before we sync the metadata, we need to free up the reserve
* block pool so that the used block count in the superblock on
* disk is correct at the end of the remount. Stash the current
* reserve pool size so that if we get remounted rw, we can
* return it to the same size.
*/
xfs_save_resvblks(mp);
xfs_quiesce_attr(mp);
mp->m_flags |= XFS_MOUNT_RDONLY;
}
return 0;
}
/*
* Second stage of a freeze. The data is already frozen so we only
* need to take care of the metadata. Once that's done sync the superblock
* to the log to dirty it in case of a crash while frozen. This ensures that we
* will recover the unlinked inode lists on the next mount.
*/
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
STATIC int
xfs_fs_freeze(
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
xfs_save_resvblks(mp);
xfs_quiesce_attr(mp);
return xfs_sync_sb(mp, true);
}
STATIC int
xfs_fs_unfreeze(
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
xfs_restore_resvblks(mp);
xfs_log_work_queue(mp);
return 0;
}
STATIC int
xfs_fs_show_options(
struct seq_file *m,
struct dentry *root)
{
return xfs_showargs(XFS_M(root->d_sb), m);
}
/*
* This function fills in xfs_mount_t fields based on mount args.
* Note: the superblock _has_ now been read in.
*/
STATIC int
xfs_finish_flags(
struct xfs_mount *mp)
{
int ronly = (mp->m_flags & XFS_MOUNT_RDONLY);
/* Fail a mount where the logbuf is smaller than the log stripe */
if (xfs_sb_version_haslogv2(&mp->m_sb)) {
if (mp->m_logbsize <= 0 &&
mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE) {
mp->m_logbsize = mp->m_sb.sb_logsunit;
} else if (mp->m_logbsize > 0 &&
mp->m_logbsize < mp->m_sb.sb_logsunit) {
xfs_warn(mp,
"logbuf size must be greater than or equal to log stripe size");
return -EINVAL;
}
} else {
/* Fail a mount if the logbuf is larger than 32K */
if (mp->m_logbsize > XLOG_BIG_RECORD_BSIZE) {
xfs_warn(mp,
"logbuf size for version 1 logs must be 16K or 32K");
return -EINVAL;
}
}
/*
* V5 filesystems always use attr2 format for attributes.
*/
if (xfs_sb_version_hascrc(&mp->m_sb) &&
(mp->m_flags & XFS_MOUNT_NOATTR2)) {
xfs_warn(mp, "Cannot mount a V5 filesystem as noattr2. "
"attr2 is always enabled for V5 filesystems.");
return -EINVAL;
}
/*
* mkfs'ed attr2 will turn on attr2 mount unless explicitly
* told by noattr2 to turn it off
*/
if (xfs_sb_version_hasattr2(&mp->m_sb) &&
!(mp->m_flags & XFS_MOUNT_NOATTR2))
mp->m_flags |= XFS_MOUNT_ATTR2;
/*
* prohibit r/w mounts of read-only filesystems
*/
if ((mp->m_sb.sb_flags & XFS_SBF_READONLY) && !ronly) {
xfs_warn(mp,
"cannot mount a read-only filesystem as read-write");
return -EROFS;
}
if ((mp->m_qflags & (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE)) &&
(mp->m_qflags & (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE)) &&
!xfs_sb_version_has_pquotino(&mp->m_sb)) {
xfs_warn(mp,
"Super block does not support project and group quota together");
return -EINVAL;
}
return 0;
}
static int
xfs_init_percpu_counters(
struct xfs_mount *mp)
{
int error;
error = percpu_counter_init(&mp->m_icount, 0, GFP_KERNEL);
if (error)
return -ENOMEM;
error = percpu_counter_init(&mp->m_ifree, 0, GFP_KERNEL);
if (error)
goto free_icount;
error = percpu_counter_init(&mp->m_fdblocks, 0, GFP_KERNEL);
if (error)
goto free_ifree;
return 0;
free_ifree:
percpu_counter_destroy(&mp->m_ifree);
free_icount:
percpu_counter_destroy(&mp->m_icount);
return -ENOMEM;
}
void
xfs_reinit_percpu_counters(
struct xfs_mount *mp)
{
percpu_counter_set(&mp->m_icount, mp->m_sb.sb_icount);
percpu_counter_set(&mp->m_ifree, mp->m_sb.sb_ifree);
percpu_counter_set(&mp->m_fdblocks, mp->m_sb.sb_fdblocks);
}
static void
xfs_destroy_percpu_counters(
struct xfs_mount *mp)
{
percpu_counter_destroy(&mp->m_icount);
percpu_counter_destroy(&mp->m_ifree);
percpu_counter_destroy(&mp->m_fdblocks);
}
STATIC int
xfs_fs_fill_super(
struct super_block *sb,
void *data,
int silent)
{
struct inode *root;
struct xfs_mount *mp = NULL;
int flags = 0, error = -ENOMEM;
mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL);
if (!mp)
goto out;
spin_lock_init(&mp->m_sb_lock);
mutex_init(&mp->m_growlock);
atomic_set(&mp->m_active_trans, 0);
INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
INIT_DELAYED_WORK(&mp->m_eofblocks_work, xfs_eofblocks_worker);
mp->m_kobj.kobject.kset = xfs_kset;
mp->m_super = sb;
sb->s_fs_info = mp;
error = xfs_parseargs(mp, (char *)data);
if (error)
goto out_free_fsname;
sb_min_blocksize(sb, BBSIZE);
sb->s_xattr = xfs_xattr_handlers;
sb->s_export_op = &xfs_export_operations;
#ifdef CONFIG_XFS_QUOTA
sb->s_qcop = &xfs_quotactl_operations;
sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
#endif
sb->s_op = &xfs_super_operations;
if (silent)
flags |= XFS_MFSI_QUIET;
error = xfs_open_devices(mp);
if (error)
goto out_free_fsname;
error = xfs_init_mount_workqueues(mp);
if (error)
goto out_close_devices;
error = xfs_init_percpu_counters(mp);
if (error)
goto out_destroy_workqueues;
/* Allocate stats memory before we do operations that might use it */
mp->m_stats.xs_stats = alloc_percpu(struct xfsstats);
if (!mp->m_stats.xs_stats) {
error = -ENOMEM;
goto out_destroy_counters;
}
error = xfs_readsb(mp, flags);
if (error)
goto out_free_stats;
error = xfs_finish_flags(mp);
if (error)
goto out_free_sb;
error = xfs_setup_devices(mp);
if (error)
goto out_free_sb;
error = xfs_filestream_mount(mp);
if (error)
goto out_free_sb;
/*
* we must configure the block size in the superblock before we run the
* full mount process as the mount process can lookup and cache inodes.
*/
sb->s_magic = XFS_SB_MAGIC;
sb->s_blocksize = mp->m_sb.sb_blocksize;
sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits);
sb->s_max_links = XFS_MAXLINK;
sb->s_time_gran = 1;
set_posix_acl_flag(sb);
/* version 5 superblocks support inode version counters. */
if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
sb->s_flags |= MS_I_VERSION;
if (mp->m_flags & XFS_MOUNT_DAX) {
xfs_warn(mp,
"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
error = bdev_dax_supported(sb, sb->s_blocksize);
if (error) {
xfs_alert(mp,
"DAX unsupported by block device. Turning off DAX.");
mp->m_flags &= ~XFS_MOUNT_DAX;
}
}
if (xfs_sb_version_hassparseinodes(&mp->m_sb))
xfs_alert(mp,
"EXPERIMENTAL sparse inode feature enabled. Use at your own risk!");
error = xfs_mountfs(mp);
if (error)
goto out_filestream_unmount;
root = igrab(VFS_I(mp->m_rootip));
if (!root) {
error = -ENOENT;
goto out_unmount;
}
sb->s_root = d_make_root(root);
if (!sb->s_root) {
error = -ENOMEM;
goto out_unmount;
}
return 0;
out_filestream_unmount:
xfs_filestream_unmount(mp);
out_free_sb:
xfs_freesb(mp);
out_free_stats:
free_percpu(mp->m_stats.xs_stats);
out_destroy_counters:
xfs_destroy_percpu_counters(mp);
out_destroy_workqueues:
xfs_destroy_mount_workqueues(mp);
out_close_devices:
xfs_close_devices(mp);
out_free_fsname:
xfs_free_fsname(mp);
kfree(mp);
out:
return error;
out_unmount:
xfs_filestream_unmount(mp);
xfs_unmountfs(mp);
goto out_free_sb;
}
STATIC void
xfs_fs_put_super(
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
xfs_notice(mp, "Unmounting Filesystem");
xfs_filestream_unmount(mp);
xfs_unmountfs(mp);
xfs_freesb(mp);
free_percpu(mp->m_stats.xs_stats);
xfs_destroy_percpu_counters(mp);
xfs_destroy_mount_workqueues(mp);
xfs_close_devices(mp);
xfs_free_fsname(mp);
kfree(mp);
}
STATIC struct dentry *
xfs_fs_mount(
struct file_system_type *fs_type,
int flags,
const char *dev_name,
void *data)
{
return mount_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super);
}
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
static long
xfs_fs_nr_cached_objects(
2013-08-28 08:18:05 +08:00
struct super_block *sb,
struct shrink_control *sc)
{
return xfs_reclaim_inodes_count(XFS_M(sb));
}
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
static long
xfs_fs_free_cached_objects(
struct super_block *sb,
struct shrink_control *sc)
{
return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan);
}
static const struct super_operations xfs_super_operations = {
.alloc_inode = xfs_fs_alloc_inode,
.destroy_inode = xfs_fs_destroy_inode,
.drop_inode = xfs_fs_drop_inode,
.put_super = xfs_fs_put_super,
.sync_fs = xfs_fs_sync_fs,
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
.freeze_fs = xfs_fs_freeze,
.unfreeze_fs = xfs_fs_unfreeze,
.statfs = xfs_fs_statfs,
.remount_fs = xfs_fs_remount,
.show_options = xfs_fs_show_options,
.nr_cached_objects = xfs_fs_nr_cached_objects,
.free_cached_objects = xfs_fs_free_cached_objects,
};
static struct file_system_type xfs_fs_type = {
.owner = THIS_MODULE,
.name = "xfs",
.mount = xfs_fs_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 11:39:14 +08:00
MODULE_ALIAS_FS("xfs");
STATIC int __init
xfs_init_zones(void)
{
xfs_ioend_bioset = bioset_create(4 * MAX_BUF_PER_PAGE,
offsetof(struct xfs_ioend, io_inline_bio));
if (!xfs_ioend_bioset)
goto out;
xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
"xfs_log_ticket");
if (!xfs_log_ticket_zone)
goto out_free_ioend_bioset;
xfs_bmap_free_item_zone = kmem_zone_init(sizeof(xfs_bmap_free_item_t),
"xfs_bmap_free_item");
if (!xfs_bmap_free_item_zone)
goto out_destroy_log_ticket_zone;
xfs_btree_cur_zone = kmem_zone_init(sizeof(xfs_btree_cur_t),
"xfs_btree_cur");
if (!xfs_btree_cur_zone)
goto out_destroy_bmap_free_item_zone;
xfs_da_state_zone = kmem_zone_init(sizeof(xfs_da_state_t),
"xfs_da_state");
if (!xfs_da_state_zone)
goto out_destroy_btree_cur_zone;
xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
if (!xfs_ifork_zone)
goto out_destroy_da_state_zone;
xfs_trans_zone = kmem_zone_init(sizeof(xfs_trans_t), "xfs_trans");
if (!xfs_trans_zone)
goto out_destroy_ifork_zone;
xfs_log_item_desc_zone =
kmem_zone_init(sizeof(struct xfs_log_item_desc),
"xfs_log_item_desc");
if (!xfs_log_item_desc_zone)
goto out_destroy_trans_zone;
/*
* The size of the zone allocated buf log item is the maximum
* size possible under XFS. This wastes a little bit of memory,
* but it is much faster.
*/
xfs_buf_item_zone = kmem_zone_init(sizeof(struct xfs_buf_log_item),
"xfs_buf_item");
if (!xfs_buf_item_zone)
goto out_destroy_log_item_desc_zone;
xfs_efd_zone = kmem_zone_init((sizeof(xfs_efd_log_item_t) +
((XFS_EFD_MAX_FAST_EXTENTS - 1) *
sizeof(xfs_extent_t))), "xfs_efd_item");
if (!xfs_efd_zone)
goto out_destroy_buf_item_zone;
xfs_efi_zone = kmem_zone_init((sizeof(xfs_efi_log_item_t) +
((XFS_EFI_MAX_FAST_EXTENTS - 1) *
sizeof(xfs_extent_t))), "xfs_efi_item");
if (!xfs_efi_zone)
goto out_destroy_efd_zone;
xfs_inode_zone =
kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode",
2016-01-15 07:18:21 +08:00
KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD |
KM_ZONE_ACCOUNT, xfs_fs_inode_init_once);
if (!xfs_inode_zone)
goto out_destroy_efi_zone;
xfs_ili_zone =
kmem_zone_init_flags(sizeof(xfs_inode_log_item_t), "xfs_ili",
KM_ZONE_SPREAD, NULL);
if (!xfs_ili_zone)
goto out_destroy_inode_zone;
xfs_icreate_zone = kmem_zone_init(sizeof(struct xfs_icreate_item),
"xfs_icr");
if (!xfs_icreate_zone)
goto out_destroy_ili_zone;
return 0;
out_destroy_ili_zone:
kmem_zone_destroy(xfs_ili_zone);
out_destroy_inode_zone:
kmem_zone_destroy(xfs_inode_zone);
out_destroy_efi_zone:
kmem_zone_destroy(xfs_efi_zone);
out_destroy_efd_zone:
kmem_zone_destroy(xfs_efd_zone);
out_destroy_buf_item_zone:
kmem_zone_destroy(xfs_buf_item_zone);
out_destroy_log_item_desc_zone:
kmem_zone_destroy(xfs_log_item_desc_zone);
out_destroy_trans_zone:
kmem_zone_destroy(xfs_trans_zone);
out_destroy_ifork_zone:
kmem_zone_destroy(xfs_ifork_zone);
out_destroy_da_state_zone:
kmem_zone_destroy(xfs_da_state_zone);
out_destroy_btree_cur_zone:
kmem_zone_destroy(xfs_btree_cur_zone);
out_destroy_bmap_free_item_zone:
kmem_zone_destroy(xfs_bmap_free_item_zone);
out_destroy_log_ticket_zone:
kmem_zone_destroy(xfs_log_ticket_zone);
out_free_ioend_bioset:
bioset_free(xfs_ioend_bioset);
out:
return -ENOMEM;
}
STATIC void
xfs_destroy_zones(void)
{
/*
* Make sure all delayed rcu free are flushed before we
* destroy caches.
*/
rcu_barrier();
kmem_zone_destroy(xfs_icreate_zone);
kmem_zone_destroy(xfs_ili_zone);
kmem_zone_destroy(xfs_inode_zone);
kmem_zone_destroy(xfs_efi_zone);
kmem_zone_destroy(xfs_efd_zone);
kmem_zone_destroy(xfs_buf_item_zone);
kmem_zone_destroy(xfs_log_item_desc_zone);
kmem_zone_destroy(xfs_trans_zone);
kmem_zone_destroy(xfs_ifork_zone);
kmem_zone_destroy(xfs_da_state_zone);
kmem_zone_destroy(xfs_btree_cur_zone);
kmem_zone_destroy(xfs_bmap_free_item_zone);
kmem_zone_destroy(xfs_log_ticket_zone);
bioset_free(xfs_ioend_bioset);
}
STATIC int __init
xfs_init_workqueues(void)
{
/*
* The allocation workqueue can be used in memory reclaim situations
* (writepage path), and parallelism is only limited by the number of
* AGs in all the filesystems mounted. Hence use the default large
* max_active value for this workqueue.
*/
xfs_alloc_wq = alloc_workqueue("xfsalloc",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0);
if (!xfs_alloc_wq)
return -ENOMEM;
return 0;
}
STATIC void
xfs_destroy_workqueues(void)
{
destroy_workqueue(xfs_alloc_wq);
}
STATIC int __init
init_xfs_fs(void)
{
int error;
xfs_check_ondisk_structs();
printk(KERN_INFO XFS_VERSION_STRING " with "
XFS_BUILD_OPTIONS " enabled\n");
xfs_dir_startup();
error = xfs_init_zones();
if (error)
goto out;
error = xfs_init_workqueues();
if (error)
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
goto out_destroy_zones;
error = xfs_mru_cache_init();
if (error)
goto out_destroy_wq;
error = xfs_buf_init();
if (error)
goto out_mru_cache_uninit;
error = xfs_init_procfs();
if (error)
goto out_buf_terminate;
error = xfs_sysctl_register();
if (error)
goto out_cleanup_procfs;
xfs_kset = kset_create_and_add("xfs", NULL, fs_kobj);
if (!xfs_kset) {
error = -ENOMEM;
goto out_sysctl_unregister;
}
xfsstats.xs_kobj.kobject.kset = xfs_kset;
xfsstats.xs_stats = alloc_percpu(struct xfsstats);
if (!xfsstats.xs_stats) {
error = -ENOMEM;
goto out_kset_unregister;
}
error = xfs_sysfs_init(&xfsstats.xs_kobj, &xfs_stats_ktype, NULL,
"stats");
if (error)
goto out_free_stats;
#ifdef DEBUG
xfs_dbg_kobj.kobject.kset = xfs_kset;
error = xfs_sysfs_init(&xfs_dbg_kobj, &xfs_dbg_ktype, NULL, "debug");
if (error)
goto out_remove_stats_kobj;
#endif
error = xfs_qm_init();
if (error)
goto out_remove_dbg_kobj;
error = register_filesystem(&xfs_fs_type);
if (error)
goto out_qm_exit;
return 0;
out_qm_exit:
xfs_qm_exit();
out_remove_dbg_kobj:
#ifdef DEBUG
xfs_sysfs_del(&xfs_dbg_kobj);
out_remove_stats_kobj:
#endif
xfs_sysfs_del(&xfsstats.xs_kobj);
out_free_stats:
free_percpu(xfsstats.xs_stats);
out_kset_unregister:
kset_unregister(xfs_kset);
out_sysctl_unregister:
xfs_sysctl_unregister();
out_cleanup_procfs:
xfs_cleanup_procfs();
out_buf_terminate:
xfs_buf_terminate();
out_mru_cache_uninit:
xfs_mru_cache_uninit();
out_destroy_wq:
xfs_destroy_workqueues();
out_destroy_zones:
xfs_destroy_zones();
out:
return error;
}
STATIC void __exit
exit_xfs_fs(void)
{
xfs_qm_exit();
unregister_filesystem(&xfs_fs_type);
#ifdef DEBUG
xfs_sysfs_del(&xfs_dbg_kobj);
#endif
xfs_sysfs_del(&xfsstats.xs_kobj);
free_percpu(xfsstats.xs_stats);
kset_unregister(xfs_kset);
xfs_sysctl_unregister();
xfs_cleanup_procfs();
xfs_buf_terminate();
xfs_mru_cache_uninit();
xfs_destroy_workqueues();
xfs_destroy_zones();
xfs_uuid_table_free();
}
module_init(init_xfs_fs);
module_exit(exit_xfs_fs);
MODULE_AUTHOR("Silicon Graphics, Inc.");
MODULE_DESCRIPTION(XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled");
MODULE_LICENSE("GPL");